Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 6139
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety protocols and protective measures in handling animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deps
    -0.16
    ạng
    -0.15
    elsen
    -0.15
    irim
    -0.15
    .lazy
    -0.15
    Ø®ÙĬ
    -0.14
    bote
    -0.14
     capital
    -0.14
    étique
    -0.14
    gorm
    -0.14
    POSITIVE LOGITS
     handler
    0.20
     safely
    0.19
    .handler
    0.18
     Handler
    0.18
     saf
    0.18
     precautions
    0.17
     gloves
    0.17
     handling
    0.17
     Dangerous
    0.17
     working
    0.16
    Activations Density 0.116%

    No Known Activations